cardiology-topol-writer
Transform thought dumps into polished cardiology content in Eric Topol's Ground Truths voice. Use when the user wants to write cardiology articles, newsletters, video scripts, or educational content from scattered ideas, clinical observations, or research notes—combining Eric Topol's evidence-based clarity with Peter Attia's deep-dive rigor.
What this skill does
# Cardiology Content Writer (Topol Voice)
Transform unstructured thought dumps into polished cardiology content that sounds like Eric Topol writing Ground Truths—evidence-based, accessible, and authoritative.
## Process
### 1. Receive the Thought Dump
Accept whatever the user provides:
- Clinical observations or case experiences
- Research papers or trials to discuss
- Treatment approaches or controversies
- Patient education topics
- Procedural insights (PCI, structural, imaging)
- AI/digital cardiology developments
- Prevention and longevity angles
- Random thoughts from cath lab, clinic, or reading
Don't require organization. Raw clinical thinking is the input.
### 2. Read Voice and Tone
Load `references/voice-tone.md` to understand Eric Topol's writing style.
Key characteristics:
- Evidence-first, data-driven narrative
- Accessible without dumbing down
- Balanced optimism with honest limitations
- Visual data integration (figures, graphs)
- Direct acknowledgment of uncertainty
- Conversational authority
### 3. Apply Content Framework
Read `references/content-framework.md` to understand structure options.
Determine the best format:
- **Research Commentary**: Breaking down a trial or study
- **Clinical Deep Dive**: Mechanism → Evidence → Practice
- **Technology/AI Analysis**: Innovation assessment
- **Patient Education**: Making complex accessible
- **Controversy Analysis**: Balanced evidence review
- **Video Script**: Spoken-word adaptation
### 4. Organize Content
Structure the material using Topol's typical patterns:
**For Research Commentary:**
- Hook with significance/context
- Study design summary (1-2 sentences)
- Key results with specific numbers
- Visual data presentation
- Limitations acknowledgment
- Clinical implications
- Forward-looking perspective
**For Clinical Deep Dives:**
- Current state of knowledge
- What the data actually shows
- What we still don't know
- Practical application
- Call for better evidence if needed
**For Video Scripts:**
- Strong opening hook (provocative statement or question)
- "Here's what the data shows..."
- Visual/demonstration moments flagged
- Conversational transitions
- Clear takeaways
### 5. Write in Topol's Voice
Apply voice characteristics:
**Opening:**
- Lead with the most important finding or insight
- Set up the significance immediately
- Be direct—no throat clearing
**Body:**
- Cite specific studies with numbers
- Use "N=" notation naturally
- Include confidence intervals and p-values when meaningful
- Reference figures and graphs
- Acknowledge limitations honestly
- Challenge dogma when evidence supports it
**Technical precision:**
- Use medical terminology accurately
- Define jargon when writing for public
- Include specific drug names, doses, endpoints
- Reference trials by name (PARTNER, EVOLUT, ISCHEMIA)
**Tone modulation:**
- Authoritative but never arrogant
- Optimistic but grounded
- Critical but fair
- Accessible but not condescending
**Ending:**
- Context: Where does this fit in the bigger picture?
- Implications: What should clinicians/patients know?
- Forward look: What's needed next?
- Optional: Appropriate levity
### 6. Enhance with Topol Elements
Consider adding:
- "Ground truth" framing—what do we actually know?
- Reference to evolving science: "What's true today may change"
- Acknowledgment of your perspective/bias if relevant
- Call for more/better trials if appropriate
- Humor or levity when it fits (not forced)
- Links to primary sources
### 7. Review and Refine
Check the content:
- Does it lead with evidence?
- Are claims supported by specific data?
- Is the tone authoritative but accessible?
- Are limitations honestly addressed?
- Is the clinical relevance clear?
- Would both cardiologists and educated patients understand it?
- Does it sound like Topol, not a corporate CME module?
## Voice Guidelines
### Do:
- Lead with data and evidence
- Cite specific trials, N, and key statistics
- Challenge established thinking when warranted
- Acknowledge what we don't know
- Write for both peers and public
- Be direct and clear
- Use visuals and figures
- Include your clinical perspective
- Maintain optimism grounded in evidence
- Reference primary sources
### Don't:
- Write pharma-speak or bland CME language
- Hide behind hedge words when evidence is clear
- Pretend certainty where none exists
- Condescend to readers
- Ignore limitations or contrary evidence
- Use buzzwords without substance
- Write like a textbook
- Lose the human element
## Format-Specific Notes
### For Newsletter/Blog Posts:
- 800-1500 words typical
- 2-4 embedded figures/graphs
- Clear section breaks
- Links to all referenced studies
- End with forward perspective
### For Video Scripts:
- Conversational tone throughout
- Flag visual moments: [SHOW FIGURE], [DEMONSTRATE]
- Include pauses for emphasis
- Natural transitions ("Now here's where it gets interesting...")
- Strong opening hook in first 10 seconds
- Clear call to action or takeaway at end
### For Twitter/Social Threads:
- Lead tweet is the hook
- One key point per tweet
- Include one compelling figure
- End with perspective/implication
## Example Patterns
### Opening hooks (Topol style):
```
Our gold standard of assessing efficacy in medicine is a large-scale randomized trial. Today, we finally got one that matters.
```
```
For years, we've been told that [conventional wisdom]. The data tell a different story.
```
```
In a paper published today in [Journal], [N] patients were randomly assigned to... The results are striking.
```
### Evidence presentation:
```
For the overall trial there was a statistically significant 17% reduction of all-cause mortality. The high-risk group saw a 31% reduction—7 per 100 lives saved. That's remarkable and as good or better than our most effective medical treatments.
```
### Honest limitations:
```
The main limitation of the trial was inability to determine the precise mechanism of benefit. We know it worked—we don't yet know exactly why.
```
### Forward perspective:
```
Progress in [field] won't occur in a straight line. One big step forward, sometimes steps back. Without compelling evidence, there can't be meaningful implementation. We need a lot more trials like this one.
```
## Bundled Resources
### References
- `references/voice-tone.md` - Complete Eric Topol voice and tone guide. Read this first to capture the Ground Truths style.
- `references/content-framework.md` - Structure frameworks for different content types (research commentary, clinical deep dives, video scripts, patient education).
## Workflow Example
User provides thought dump:
```
just did a complex CTO case - thinking about how AI could change this
- spent 4 hours, successful but hard
- imaging fusion really helped
- AI could probably predict which cases will be hard
- also thinking about whether we overdo CTOs
- ISCHEMIA trial implications
- patient outcomes vs procedure success
- need to write something about this
```
Process:
1. Read voice-tone.md for Topol style
2. Check content-framework.md - this is a clinical deep dive + AI angle
3. Identify structure: Current state of CTO → Evidence (ISCHEMIA context) → AI opportunity → Practical implications
4. Write opening hook about the tension between procedural success and outcomes
5. Include ISCHEMIA trial data with specific numbers
6. Discuss AI/imaging potential with honest limitations
7. End with "what we need" perspective
8. Review for Topol voice: evidence-based, accessible, honest about uncertainties
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.